[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-1-en-105":3,"doc-seo-164522-105":53,"doc-detail-164522-en":126},{"code":4,"msg":5,"data":6},0,"success",[7,14,19,24,29,34,39,44,49],{"id":8,"doc_module":9,"doc_module_name":10,"category_name":11,"show_sort_weight":12,"slug":13},11,1,"Template","Presentations",90,"presentations",{"id":15,"doc_module":9,"doc_module_name":10,"category_name":16,"show_sort_weight":17,"slug":18},12,"Resumes",80,"resumes",{"id":20,"doc_module":9,"doc_module_name":10,"category_name":21,"show_sort_weight":22,"slug":23},14,"Invoices",70,"invoices",{"id":25,"doc_module":9,"doc_module_name":10,"category_name":26,"show_sort_weight":27,"slug":28},15,"Posters",60,"posters",{"id":30,"doc_module":9,"doc_module_name":10,"category_name":31,"show_sort_weight":32,"slug":33},16,"Social Media",50,"social-media",{"id":35,"doc_module":9,"doc_module_name":10,"category_name":36,"show_sort_weight":37,"slug":38},17,"Forms",40,"forms",{"id":40,"doc_module":9,"doc_module_name":10,"category_name":41,"show_sort_weight":42,"slug":43},18,"Letters",30,"letters",{"id":45,"doc_module":9,"doc_module_name":10,"category_name":46,"show_sort_weight":47,"slug":48},21,"Paper Templates",5,"papers-templates",{"id":50,"doc_module":9,"doc_module_name":10,"category_name":51,"show_sort_weight":4,"slug":52},158,"General","general-158",{"code":4,"msg":54,"data":55},"ok",{"site_id":56,"language":57,"slug":58,"title":59,"keywords":60,"description":61,"schema_data":62,"social_meta":119,"head_meta":121,"extra_data":123,"updated_unix":125},105,"en","supplementary-material-machine-learning","Supplementary Material - Machine Learning","","Supplementary material outlining the foundations of machine learning and its application to real-world, data-intensive domains. It explains how algorithms learn patterns from large datasets without explicit programming, why human inspection may be needed, and the trade-offs between interpretable methods and deep learning. The document then organizes core learning paradigms—supervised, unsupervised, semi-supervised, and reinforcement—followed by supervised learning workflows, typical task types, and key risks such as overfitting, with approaches like feature selection and feature extraction.",{"@graph":63,"@context":118},[64,80,101],{"@type":65,"itemListElement":66},"BreadcrumbList",[67,71,74,77],{"item":68,"name":69,"@type":70,"position":9},"https://docshare.wps.com","Home","ListItem",{"item":72,"name":10,"@type":70,"position":73},"https://docshare.wps.com/template/",2,{"item":75,"name":51,"@type":70,"position":76},"https://docshare.wps.com/template/general/",3,{"item":78,"name":59,"@type":70,"position":79},"https://docshare.wps.com/template/supplementary-material-machine-learning/164522/",4,{"url":78,"name":59,"@type":81,"image":82,"author":87,"headline":59,"publisher":90,"fileFormat":93,"inLanguage":57,"description":61,"dateModified":94,"datePublished":95,"encodingFormat":93,"isAccessibleForFree":96,"interactionStatistic":97},"DigitalDocument",{"url":83,"@type":84,"width":85,"height":86},"https://docshare.wps.com/thumbnails/supplementary-material-machine-learning/164522.png","ImageObject",442,249,{"name":88,"@type":89},"Rizky","Person",{"url":68,"name":91,"@type":92},"DocShare","Organization","application/vnd.openxmlformats-officedocument.wordprocessingml.document","2026-09-21","2026-08-31",true,{"@type":98,"interactionType":99,"userInteractionCount":73},"InteractionCounter",{"@type":100},"ViewAction",{"@type":102,"mainEntity":103},"FAQPage",[104,110,114],{"name":105,"@type":106,"acceptedAnswer":107},"What is the main idea behind machine learning in this material?","Question",{"text":108,"@type":109},"Machine learning uses computers and algorithms to process large amounts of data and identify patterns without explicit human programming. Models improve iteratively to discover new information, but results should be inspected by experts to confirm performance.","Answer",{"name":111,"@type":106,"acceptedAnswer":112},"How do supervised and unsupervised learning differ?",{"text":113,"@type":109},"Supervised learning learns from labeled data to map inputs to known outcomes, making it suitable for tasks with clear goals. Unsupervised learning finds patterns and structures in data without using labels or categories, typically requiring large datasets.",{"name":115,"@type":106,"acceptedAnswer":116},"What causes overfitting in machine learning, and how can it be addressed?",{"text":117,"@type":109},"Overfitting occurs when a model is trained too closely to the training data, making predictions on new data incorrect. Feature selection and feature extraction during preprocessing are described as ways to tackle this challenge.","https://schema.org",{"og:url":78,"og:type":120,"og:title":59,"og:site_name":91,"og:description":61},"article",{"robots":122,"canonical":78},"index,follow",{"doc_id":124,"site_id":56},164522,1788154847,{"code":4,"msg":5,"data":127},{"doc_id":124,"user_id":128,"nickname":88,"user_avatar":129,"doc_module":9,"category_id":50,"category_name":51,"doc_title":59,"doc_description":61,"doc_content":130,"file_id":131,"file_url":132,"file_type":133,"file_size":134,"view_count":73,"is_deleted":4,"is_public":9,"is_downloadable":9,"audit_status":9,"page_count":45,"language":135,"language_code":57,"site_id":56,"html_lang":57,"table_of_contents":136,"faqs":137,"seo_title":138,"seo_description":61,"update_tm":125,"read_time":139},962085564807,"https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8","Supplementary Material – Machine Learning\nMachine Learning Overview\nMachine learning involves using computers and algorithms to process large amounts of data (observations, patient characteristics, and measurements) and identify patterns without explicit human programming.1 The strength of machine learning is its ability to sieve through massive amounts of data to find new information and insights by iteratively improving its model without assumed relationships. Since the methods perform without explicit programming, the results require an inspection from a human expert to determine whether the algorithms are performing as expected. Interpretable machine learning algorithms can simplify this task. Machine learning algorithms can model and provide insights into a very wide range of data, including genomics,2–4 images,5–7 sound recordings,8,9 vital signs,10 and electronic health records data collected in primary,11,12 secondary,13 and tertiary care.14\nMachine learning is an umbrella term, consisting of tools and techniques that use data to learn how to perform a given task. It is commonly used in data science to model and describe large amounts of data, and to predict events or measurements of interest without any assumption of the relationship between the predictors and the predictions (a priori knowledge). Also, it can model very complex, non-linear, relationships that are not possible with regression analysis. Although most machine learning algorithms applied to asthma management with mHealth use traditional supervised and unsupervised learning techniques, some studies have also used various deep learning approaches (see Supplementary Figures 1 and 2 for a schematic overview of machine learning). In the current study, we refer to traditional machine learning methods as those that require explicit feature engineering (either done manually or using additional machine learning algorithms for feature extraction and selection). Traditional machine learning methods include supervised learning techniques such as logistic regression, support vector machine (SVM), and decision trees. In contrast, increasingly popular methods (such as deep learning) creates new features within the model while finding the best fit to the data.15 Although, deep learning was conceptualized decades ago,15,16 it has only become computationally feasible around the turn of the millennium. It can be used to model the same data as traditional machine learning with better performance and without prior domain knowledge, but the models are harder to interpret, which has limited its widespread adoption.\nSupervised learning refers to algorithms that learn to label or categorize data that is already labelled. This approach is suitable for tasks that have a well-defined goal such as predicting outcomes. Unsupervised learning, on the other hand, refers to algorithms that describe patterns and structures in the data without following the lead of labels or categories. Such methods typically require large amount of data. If only some data is labelled, such as with medical images that requires an expert to label, semi-supervised learning can be used to leverage the benefits of supervised and unsupervised learning. Reinforcement learning refers to algorithms that examines how a computer agent would interact with an environment to maximize a reward. An example application of reinforcement learning is the AlphaGo Zero that learnt to play the board game of Go at a super-human level through self-play with no knowledge but the rules of the game.17 Deep learning is a class of machine learning algorithms that have been driving the latest wave of AI publicity, because they can be applied to almost any application given the right data and sufficient computing power.\nA common challenge to machine learning is overfitting, which is where the model is trained to the data too closely such that its predictions on new data becomes incorrect. Including features selection and feature extract","cbCaioXhociO0imu","https://ap.wps.com/l/cbCaioXhociO0imu","docx",400751,"English","# Machine Learning Overview\n## Learning as Pattern Discovery\n## Learning Paradigms\n# Supervised Learning\n## Task Types and Workflow\n## Common Algorithms\n## Overfitting and Mitigation","[{\"question\":\"What is the main idea behind machine learning in this material?\",\"answer\":\"Machine learning uses computers and algorithms to process large amounts of data and identify patterns without explicit human programming. Models improve iteratively to discover new information, but results should be inspected by experts to confirm performance.\"},{\"question\":\"How do supervised and unsupervised learning differ?\",\"answer\":\"Supervised learning learns from labeled data to map inputs to known outcomes, making it suitable for tasks with clear goals. Unsupervised learning finds patterns and structures in data without using labels or categories, typically requiring large datasets.\"},{\"question\":\"What causes overfitting in machine learning, and how can it be addressed?\",\"answer\":\"Overfitting occurs when a model is trained too closely to the training data, making predictions on new data incorrect. Feature selection and feature extraction during preprocessing are described as ways to tackle this challenge.\"}]","Supplementary Material - Machine Learning | DOCX",7]